PoC .NET Tensorflow

A proof of concept (PoC) to demonstrate the integration of .NET Core and TensorFlow for real-time image recognition.

Introduction

This project showcases the power of .NET Core combined with TensorFlow to perform real-time image recognition. Using TensorFlow’s model inference capabilities, the PoC allows users to process images and identify objects in real-time.

The implementation is inspired by Paulo Torres’ Medium article, with enhancements to demonstrate practical use cases.

Diagram

graph TD
    A[Input Device Camera/Local Images] -->|Image Data| B[.NET Core App]
    B -->|Pre-Processing| C[TensorFlow Model]
    C -->|Model Inference| D[Recognition Results]
    D -->|Output| E[Display/Logging]

Features

Real-Time Image Processing: Capture images from a live camera feed or load pre-saved images.
TensorFlow Integration: Leverage TensorFlow models for accurate object detection.
Platform Independence: Built using .NET Core for cross-platform support.
Extensible Design: Easy to integrate with different TensorFlow models and extend for additional functionality.

Useful Links

How to Run

Clone the repository:

git clone https://github.com/your-repository-url.git
cd your-repository-folder

Install prerequisites:
- Ensure you have .NET Core SDK installed (Download).
- Install TensorFlow runtime for your platform.
Restore dependencies:
```
dotnet restore
```
Build the project:
```
dotnet build
```
Run the application:
```
dotnet run
```
Usage:
- Provide an image input (via file or live camera feed).
- Observe real-time recognition results in the console or UI.

License

This project is licensed under the MIT License. See the LICENSE file for details.